vsbuffalo

The Ten Commandments of Scientific Coding

1. Thou shall use version control.

2. Thou shall comment thy code.

3. Thou shall use existing libraries whenever possible.

4. Thou shall try to unit test.

vsbuffalo

# hmmerfix.py - fix terrible output format (fixed width) of HMMER

# We make a simple assumption about the data: any non-delimiter spaces
# are in the last column. Under this assumption, we build a regular
# expression programmatically with strict types. Strict typing and the
# number of grouped elements ensure some safety.

import re
import sys
from collections import OrderedDict

vsbuffalo

/* 
(c) Vince Buffalo, 2012; License: GPL.
I compile this on my system (OS X with samtools installed via Homebrew) with:

    clang -g -lz -L/usr/local/Cellar/samtools/0.1.18/lib/ -lbam -I/usr/local/Cellar/samtools/0.1.18/include/bam/ -o mapqcov mapqcov.c

But you'll likely need to compile differently for you libraries. This code works and is consistent with the slower results from mpileup. This is just a standalone beta; it will likely be incorporated into something else.
*/

#include <stdio.h>

vsbuffalo

tail -f your_mapping.sam |  bioawk -csam 'BEGIN{total=0;mapped=0} {total = total + 1; mapped = mapped + !and($flag, 4); if (total % 100 == 0) { printf "\tmapping rate: %f\r",mapped/total }}'

vsbuffalo

"""

Generate a IUPAC nucleotide table. The order is a modification of Heng
Li's. I have added '-' to mean gap. X means non-IUPAC character and
can be a useful warning.

"""
import sys
rev_iupac = "XACMGRSVTWYHKDBN-"
rev_iupac_alt = "xacmgrsvtwyhkdbn."

vsbuffalo

#!/bin/bash
# trim.sh - generic, slightly insane paired end quality trimming script
# Vince Buffalo <[email protected]> (sans poly-A)
set -e
set -u

## pre-config
ADAPTERS=illumina_adapters.fa
SAMPLE_NAME=some_sample_name
IN1=in1.fastq

vsbuffalo

# use GNU screen's C-a binding, since it's programmed in my brain
set-option -g prefix C-a
unbind C-b

# use GNU screen's C-a C-a for last window
bind-key C-a last-window

# use 1-based indexing, since 1 is close
set -g base-index 1

vsbuffalo

import numpy as np
from itertools import combinations
from collections import Counter
import datetime as dt

np.random.seed(0)

def repeat_mutation_sim(G, N, L, mu=3e-8):
    """
    Generate N repeats of length L mutating at rate

vsbuffalo

import sys
from readfq import readfq
from itertools import combinations
from datetime import datetime

def num_shared(seq_a, seq_b, consensus_seq):
    """
    Given two alignment sequences in multiple alignment FASTA format,
    calculate the number of shared SNPs (for minor alleles only, not 
    in consensus).

vsbuffalo

"""
entropy.py

Calculate entropy of a given list.
"""
from math import log, log10
from collections import Counter
import pdb

def entropy(x, logfun=lambda x: log(x, 2)):